Friday, December 30, 2022

The pitfalls of defining neural correlates of brain functions

Rust and Le Doux do a useful brief opinion piece from which I pass on two clips, and recommend you read the whole open source text.
...neuroscientists should avoid conflating circuits that control behavior with mental states, especially in the absence of evidence that the two map onto one another. These equivalencies need to be very carefully investigated rather than presumed.
Considerable evidence suggests that circuits involving the amygdala control behavioral and physiological responses to threats. In animal research labs, threats are often recapitulated by pairing a tone with an aversive stimulus such as a weak shock to elicit ‘fear-related behaviors’ such as freezing upon hearing the tone again. The neural circuits that learn the association between the tone and shock and produce freezing behavior are among the best understood in the brain. The problem lies in labeling these circuits with the term ‘fear’, because it presumes that the threat elicits a mental state, a subjective experience, of fear that is caused by activity in the amygdala. However, mounting evidence suggests that the amygdala is not required for the mental state of fear. Instead, the mental state of fear crucially depends, at least in part, on cortical circuits that interpret or conceptualize what is occurring in the social and physical environment and in one’s body. In this framework, amygdala circuits control nonconscious defense behaviors (such as freezing) as opposed to conscious experience. Should this framework be correct, the extensive ongoing efforts devoted to targeting amygdala circuits and rodent behaviors such as freezing and avoidance are unlikely to provide a direct route to treatments for human fear and anxiety disorders. These lines of research can help, but not without recognizing the centrality of subjective experience.

Wednesday, December 28, 2022

Wormholes in quanturm computers

I pass on this link to a YouTube video sent out by the Chaos and Complex Systems Discussion group at the University of Wisconsin. Totally fun to watch, but I don't think any of us understand it.

Monday, December 26, 2022

Rigorous study does not find that exercise and mindfulness training improve cognitive function in older adults.

Wow, here is a study by Lenze et al. - not confirming the results of numerous other less rigorous studies reported in MindBlog posts - that is unable to demonstrate that the use of mindfulness training, exercise, or a combination of both can significantly improving cognitive function in older adults with subjective cognitive concerns. In their randomized clinical trial that included 585 participants, mindfulness training, exercise, or both did not result in significant differences in improvement in episodic memory or executive function composite scores at 6 months. Gretchen Reynolds provides context and a summary of the work in a Washington Post article.

Friday, December 23, 2022

A smart phone intervention that enhances memory in older adults.

Martin et al.  offer an open source article that describes a smartphone intervention that enhances real-world memory and promotes differentiation of hippocampal activity in older adults.  I have downloaded the HippoCamera smartphone App described in the text from the Apple App Store, and found a research passcode is required, for which the following clip of text from the article is relevant: "As of the time of writing, this is a research-dedicated application that requires an access code that can be obtained from a corresponding author."


The ability to vividly recollect our past declines with age, a trend that negatively impacts overall well-being. We show that using smartphone technologies to record and replay brief but rich memory cues from daily life can improve older adults’ ability to reexperience the past. This enhancement was associated with corresponding changes in the way memories were stored in the brain. Functional neuroimaging showed that repeatedly replaying memory cues drove memories apart from one another in the hippocampus, a brain region with well-established links to memory function. This increase in differentiation likely facilitated behavior by strengthening memory and minimizing competition among different memories at retrieval. This work reveals an easy-to-use intervention that helps older adults better remember their personal past.
The act of remembering an everyday experience influences how we interpret the world, how we think about the future, and how we perceive ourselves. It also enhances long-term retention of the recalled content, increasing the likelihood that it will be recalled again. Unfortunately, the ability to recollect event-specific details and reexperience the past tends to decline with age. This decline in recollection may reflect a corresponding decrease in the distinctiveness of hippocampal memory representations. Despite these well-established changes, there are few effective cognitive behavioral interventions that target real-world episodic memory. We addressed this gap by developing a smartphone-based application called HippoCamera that allows participants to record labeled videos of everyday events and subsequently replay, high-fidelity autobiographical memory cues. In two experiments, we found that older adults were able to easily integrate this noninvasive intervention into their daily lives. Using HippoCamera to repeatedly reactivate memories for real-world events improved episodic recollection and it evoked more positive autobiographical sentiment at the time of retrieval. In both experiments, these benefits were observed shortly after the intervention and again after a 3-mo delay. Moreover, more detailed recollection was associated with more differentiated memory signals in the hippocampus. Thus, using this smartphone application to systematically reactivate memories for recent real-world experiences can help to maintain a bridge between the present and past in older adults.

Wednesday, December 21, 2022

Neurocomputational evidence that conflicting prosocial motives guide distributive justice

A fascinating perspective and analysis from Hu et al. who show that three prosocial motives (fairness, harm aversion, and rank reversal aversion) are encoded by separate neural systems, compete for representation in various brain areas processing equality and harm signals, and are integrated in the striatum, which functions as a crucial hub for translating the motives to behavior (see also the commentary by Armstrong and McKee).  


Resource allocation in human societies usually triggers discussions about fairness, but satisfactory solutions to distribution problems also involve other prosocial motives that may prescribe different actions. Here, we address how the human brain mitigates such conflicts between multiple prosocial motives (fairness, harm aversion, and rank reversal aversion) during wealth distribution. Combining a experimental paradigm with fMRI and integrated neurocomputational modeling, we show that different prosocial motives are separately represented and integrated into choices by neural activity in striatum and its interactions with different brain regions. These findings extend unidimensional economic theories of third-party social preferences, characterize biological bases for individual and contextual differences in resource distribution behavior, and have economic and political implications for the design of taxation policies.
In the history of humanity, most conflicts within and between societies have originated from perceived inequality in resource distribution. How humans achieve and maintain distributive justice has therefore been an intensely studied issue. However, most research on the corresponding psychological processes has focused on inequality aversion and has been largely agnostic of other motives that may either align or oppose this behavioral tendency. Here we provide behavioral, computational, and neuroimaging evidence that distribution decisions are guided by three distinct motives—inequality aversion, harm aversion, and rank reversal aversion—that interact with each other and can also deter individuals from pursuing equality. At the neural level, we show that these three motives are encoded by separate neural systems, compete for representation in various brain areas processing equality and harm signals, and are integrated in the striatum, which functions as a crucial hub for translating the motives to behavior. Our findings provide a comprehensive framework for understanding the cognitive and biological processes by which multiple prosocial motives are coordinated in the brain to guide redistribution behaviors. This framework enhances our understanding of the brain mechanisms underlying equality-related behavior, suggests possible neural origins of individual differences in social preferences, and provides a new pathway to understand the cognitive and neural basis of clinical disorders with impaired social functions.

Monday, December 19, 2022

Can we move beyond social media's current destruction of civil society?

I strongly recommend that you read Ezra Klein's NYTimes essay on Twitter. He begins by noting that the metaphor of Twitter as a global town square is wrong on three levels. I pass on some clips:
First, there isn’t, can’t be and shouldn’t be a “global town square.” The world needs many town squares, not one. Public spaces are rooted in the communities and contexts in which they exist. This is true, too, for Twitter, which is less a singular entity than a digital multiverse. What Twitter is for activists in Zimbabwe is not what it is for gamers in Britain.
Second, town squares are public spaces, governed in some way by the public. That is what makes them a town square rather than a square in a town. They are not the playthings of whimsical billionaires. They do not exist, as Twitter did for so long, to provide returns to shareholders...A town square controlled by one man isn’t a town square. It’s a storefront, an art project or possibly a game preserve.
Third, what matters for a polity isn’t the mere existence of a town square but the condition the townspeople are in when they arrive. Town squares can host debates. They can host craft fairs. They can host brawls. They can host lynchings. Civilization does not depend on a place to gather. It depends on what happens when people gather.
Twitter has real strengths, many of which are the flip side of its weaknesses. It is as flat a medium as any that has existed. It is as fast a medium as has ever existed; that can be maddening, but it can also draw attention to something that is happening and has to change right now. It is an unusually confrontational medium, and that has permitted movements like Black Lives Matter and #MeToo to flower and for socialists to get a new hearing in American politics — and it has also, of course, given new succor and life to the racist right. Put simply, Twitter’s value is how easy it makes it to talk. Its cost is how hard it makes it to listen.
It is a failure of imagination to think that our choice is the social media platforms we have now or nothing. I keep thinking about something that Robin Sloan, a novelist and former Twitter employee, wrote this year: “There are so many ways people might relate to one another online, so many ways exchange and conviviality might be organized. Look at these screens, this wash of pixels, the liquid potential! What a colossal bummer that Twitter eked out a local maximum, that its network effect still (!) consumes the fuel for other possibilities, other explorations.”
What’s surprised me most as Twitter has convulsed in recent weeks is how threadbare the social media cupboard really is. So many are open to trying something new, but as of yet, there’s nothing that feels all that new to try. Everything feels like a take on Twitter. It may be faster or slower, more decentralized or more moderated, but they’re all variations on the same theme: experiments in how to capture attention rather than deepen it, platforms built to encourage us to speak rather than to help us listen or think.
We do not make our best decisions, as individuals or as a collective, when our minds are most active and fretful. And yet “active and fretful” is about as precise a description as I can imagine of the Twitter mind. And having put us in an active, fretful mental state, Twitter then encourages us to fire off declarative statements on the most divisive possible issues, always with one eye to how quickly they will rack up likes and retweets and thus viral power. It’s insane.
And it will get so much worse from here. OpenAI recently released ChatGPT, an artificial intelligence system that can be given requests in plain language and spit out remarkably passable results...What ChatGPT can do is a marvel. We are at the dawn of a new technological era. But it is easy to see how it could turn dark — and quickly. A.I. systems like this make the production and manipulation of text (and code and images and eventually audio and video) functionally costless. They will be deployed to produce whatever makes us most likely to click. But these systems do not and cannot know what they are producing. The cost of creating and optimizing content that grabs our attention is plummeting, but the cost of producing valuable and truthful work isn’t.
These are technologies that lend themselves to cacophony, not community. I fear a world in which the business models behind them run on our attention or profit off our anger. But other worlds and other models are possible.
In Taiwan, as described by Audrey Tang, Taiwan’s minister of digital affairs, key parts of digital infrastructure are managed at the level of what we sometimes call civil society — the layer of associations and organizations between the government and the market.. The PTT Bulletin Board System is still owned by the student group that started it. It was part of how Taiwan responded so early and so effectively to the coronavirus. “It has no shareholders,” Tang said. “No advertisers. It is entirely within the academic network. It’s entirely open source. It's entirely community governed. People can freely join it. It’s a public digital space.”
Wikipedia remains one of the most-visited sites on the web, and it is owned and managed by the nonprofit Wikimedia Foundation. It shows. Wikipedia has never tried to become more than it is. It never pivoted to video or remade itself around an algorithmic feed in order to harvest more of our attention. It is a commons but one that is governed so we may use it rather than so that it may use us. It gives so much more than it takes. It thrives, quietly and gently, as a reminder that a very different internet, governed in a very different way, intended for a very different purpose, is possible.
There are those who believe the social web is reaching its terminal point. I hope they’re right. Platform after platform was designed to make it easier and more addictive for us to share content with one another so the corporations behind them could sell ever more of our attention and data. In different ways, most of these platforms are now in decline.
What if the next turn of the media dial was measured not by how much attention we gave to a platform but by how much it gave to us? I am not sure what such a service would look like. But I am hungry for it, and I suspect a lot of other people are, too.

Friday, December 16, 2022

The dawn of mediocre computing.

This post is a followup on MindBlog's 12/07/22 post on OpenAI's ChatGPT essay generating system. It was mentioned in Venkatesh Rao's essay "The Dawn of Mediocre Computing" that my techie son, Jonathan Bownds,sent to me. After pasting in the first two paragraphs of Rao's article, I want to pass on some essential clips that Jon extracted from Rao's overly long text, the sort of logorrheic writing that is responsible for the TLDR (too long didn't read) acronym. 

Well, we all knew it was coming. Computers already easily overwhelm the best humans at chess and Go. Now they have done something far harder: achieved parity with David Brooks at writing.
OpenAI’s ChatGPT, released as a research beta two days ago, has done to the standard high-school essay what cameras did to photorealistic painting and pocket calculators did to basic arithmetic. It is open sign-up and free for now, but I suspect not for much longer, so go try it; and make sure to trawl social media for interesting and revealing examples being posted by people.


Mediocre computing is computing that aims for parity with mediocre human performance in a realish domains where notions of excellence are ill-posed.
Excellent computing is computing that aims to surpass the best-performing humans in stylized, closed-world domains where notions of excellence are well-posed.
Most of us spend most of our time in realish domains. The urban built environment, workplaces, shopping, and modern systems of roads are all examples of realish domains. But I want to focus on two big and important ones in particular: language and money. Vast numbers of mediocre humans make good livings producing words and/or moving money around. These activities are also the home domains of the two frontiers of computing today, Al and crypto. The Second and First Foundations of the mediocre future of computing.
Via seemingly unrelated computational pathways, these two realish domains have succumbed to computerized automation. Incompletely, imperfectly, and unreliably, to be sure, but they definitely have succumbed. And in ways that seem conceptually roughly right rather than not even wrong. Large language models (LLMs) are the right way for software to eat language. Blockchains are the right way for software to eat money. And the two together are the right way to eat everything from contracts to code.
This reeks of real yin-yangery that extends to the roots of computing somehow. It's not just me hallucinating patterns where there are none.
I'm not trying to be cute here. I sincerely believe mediocre computing in realish domains is not just harder than excellent computing in stylized domains, but constitutes a whole higher category of hardness. There is an element of Moravec's paradox in my reasoning here. Roughly, the paradox states that tasks that look simple, and which all humans can do, are harder for Als than tasks that look hard, and which seem like exceptional achievements among humans.

Wednesday, December 14, 2022

Individuals prefer to harm their own group rather than help an opposing group

From Gershon and Fridman:  


Understanding the principles guiding decisions in intergroup conflicts is essential to recognizing the psychological barriers to compromise and cooperation. We introduce a novel paradigm for studying group decision-making, demonstrating that individuals are so averse to supporting opposing groups that they prefer equivalent or greater harm to their own group instead. While previous models of group decision-making claim that group members are driven by a desire to benefit their in-group (“in-group love”) rather than harm their out-group, our results cannot be explained by in-group love or by a harm minimizing strategy. Instead, we propose that identity concerns drive this behavior. Our theorizing speaks to research in psychology, political theory, and negotiations by examining how group members navigate trade-offs among competing priorities.
Group-based conflict enacts a severe toll on society, yet the psychological factors governing behavior in group conflicts remain unclear. Past work finds that group members seek to maximize relative differences between their in-group and out-group (“in-group favoritism”) and are driven by a desire to benefit in-groups rather than harm out-groups (the “in-group love” hypothesis). This prior research studies how decision-makers approach trade-offs between two net-positive outcomes for their in-group. However, in the real world, group members often face trade-offs between net-negative options, entailing either losses to their group or gains for the opposition. Anecdotally, under such conditions, individuals may avoid supporting their opponents even if this harms their own group, seemingly inconsistent with “in-group love” or a harm minimizing strategy. Yet, to the best of our knowledge, these circumstances have not been investigated. In six pre-registered studies, we find consistent evidence that individuals prefer to harm their own group rather than provide even minimal support to an opposing group across polarized issues (abortion access, political party, gun rights). Strikingly, in an incentive-compatible experiment, individuals preferred to subtract more than three times as much from their own group rather than support an opposing group, despite believing that their in-group is more effective with funds. We find that identity concerns drive preferences in group decision-making, and individuals believe that supporting an opposing group is less value-compatible than harming their own group. Our results hold valuable insights for the psychology of decision-making in intergroup conflict as well as potential interventions for conflict resolution.

Monday, December 12, 2022

Autism attenuates the perception of the mind-body divide

A fascinating piece of work from Berent et al.:  


Across cultures, people consider the mind as ethereal, distinct from the body. But whether Dualism arises only from culture (nurture) or also spontaneously (from human nature) is unknown. To address this question, here, we turn to autism spectrum disorder (ASD)—a congenital disorder that compromises intuitive reasoning about the minds of others (theory of mind, ToM). If ToM promotes Dualist reasoning, then Dualist reasoning ought to be attenuated in ASD. Our results show that, compared to controls, people with ASD are more likely to view bodies and minds alike (in line with Physicalism). Moreover, a Physicalist stance is linked to difficulties with ToM. These results shed light on ASD and on the mind-body distinction in humans.
People are intuitive Dualists—they tacitly consider the mind as ethereal, distinct from the body. Here we ask whether Dualism emerges naturally from the conflicting core principles that guide reasoning about objects, on the one hand, and about the minds of agents (theory of mind, ToM), on the other. To address this question, we explore Dualist reasoning in autism spectrum disorder (ASD)—a congenital disorder known to compromise ToM. If Dualism arises from ToM, then ASD ought to attenuate Dualism and promote Physicalism. In line with this prediction, Experiment 1 shows that, compared to controls, people with ASD are more likely to view psychological traits as embodied—as likely to manifest in a replica of one’s body. Experiment 2 demonstrates that, unlike controls, people with ASD do not consider thoughts as disembodied—as persistent in the afterlife (upon the body’s demise). If ASD promotes the perception of the psyche as embodied, and if (per Essentialism) embodiment suggests innateness, then ASD should further promote Nativism—this bias is shown in Experiment 3. Finally, Experiment 4 demonstrates that, in neurotypical (NT) participants, difficulties with ToM correlate with Physicalism. These results are the first to show that ASD attenuates Dualist reasoning and to link Dualism to ToM. These conclusions suggest that the mind-body distinction might be natural for people to entertain.

Friday, December 09, 2022

How modern human brains are different from those of other hominids and chimps.

Work pointed to in the previous post continues to add to the list of behaviors once presumed to be unique to humans that have now been found in other animals (morality, having a ‘self’, etc.) Previous MindBlog posts (list, von Economo neurons etc. do search..) have noted emerging evidence for brain features unique to - or much more pronounced in - humans than other primates. Now Pinson et al. have found that a single amino acid change in the transketolase-like 1 (TKTL1) protein on production of basal radial glia, the workhorses that generate much of the neocortex, appears that the modern human has more neocortex to work with than the ancient Neanderthal did. Here is their abstract:
Neanderthal brains were similar in size to those of modern humans. We sought to investigate potential differences in neurogenesis during neocortex development. Modern human transketolase-like 1 (TKTL1) differs from Neanderthal TKTL1 by a lysine-to-arginine amino acid substitution. Using overexpression in developing mouse and ferret neocortex, knockout in fetal human neocortical tissue, and genome-edited cerebral organoids, we found that the modern human variant, hTKTL1, but not the Neanderthal variant, increases the abundance of basal radial glia (bRG) but not that of intermediate progenitors (bIPs). bRG generate more neocortical neurons than bIPs. The hTKTL1 effect requires the pentose phosphate pathway and fatty acid synthesis. Inhibition of these metabolic pathways reduces bRG abundance in fetal human neocortical tissue. Our data suggest that neocortical neurogenesis in modern humans differs from that in Neanderthals.

Wednesday, December 07, 2022

OpenAI’s ChatGPT answers some questions from MindBlog

Given a recent posting in which I played with the DALL-E 2 A.I. system that generates images when you tell it what you want to see, I was motivated by a Venkatesh Rao essay "The Dawn of Mediocre Computing" to try out an essay generating system - OpenAI's ChatGPT, released as a research beta several days ago. After puttering through a number of references and joining the OpenAI Discord Server, I fundamentally don't get it and have nothing original to pass on in this post, but I thought some MindBlog readers might enjoy spending some time in the rabbit hole I am just now exiting. I pass on the following MindBlog queries and ChatGPT's rather remarkable replies: 

Question: what is the predictive processing model for brain function? 

The predictive processing model is a framework for understanding how the brain works. It proposes that the brain is constantly generating predictions about the world around us and that these predictions are used to inform our perception, behavior, and action. According to this model, the brain is always trying to make sense of the sensory information it receives by comparing it to its internal models and predictions. If there is a mismatch between the sensory information and the brain's predictions, this can lead to the experience of surprise or prediction error. The brain then uses this prediction error to update its internal models and make more accurate predictions in the future. This process is thought to be the basis for how we learn and adapt to our environment. 

Question: What are the main models for brain function? 

There are many different models or frameworks for understanding how the brain works, each of which offers a different perspective on brain function. Some of the most prominent and well-known models include the following:

The neural network model, which proposes that the brain is composed of interconnected networks of neurons that communicate with each other through electrical and chemical signals.
The cognitive model, which emphasizes the role of higher-level cognitive processes such as attention, memory, and decision-making in brain function.
The computational model, which views the brain as a biological computer that processes information using algorithms and rules.
The systems model, which focuses on the ways in which different brain regions and systems interact to produce complex behaviors and mental states.
The evolutionary model, which emphasizes the role of natural selection in shaping the brain and its functions.
The dynamic systems model, which proposes that the brain is a complex, self-organizing system that is constantly adapting and changing in response to experience. 

Each of these models offers a different perspective on brain function and can be used to help understand different aspects of the brain and its behavior.

Question: Explain critical race theory 

Critical race theory is a school of thought that explores the ways in which race and racism affect and are embedded in the laws, policies, and social structures of society. It is a framework for understanding how society and its institutions can perpetuate inequality along racial lines, and it emphasizes the importance of examining the interplay between race, power, and the law. Critical race theory is often used as a lens for analyzing issues related to inequality and social justice. It is a critical approach to the study of race and racism that seeks to challenge and dismantle the ways in which race and racism operate in society. 

ADDENDUM: I suggest readers have a look at this article on "Sentience and Sensibility"

Monday, December 05, 2022

A collection of animal stories

I've accumulated several items on animal behaviors in my list of potential post subjects, and have decided to simply pass them on to allow animal curious MindBlog readers to have a look. 

Farad Manjoo notes that ants, not humans, own the world. 

Not only land animals like humans toss objects at irritating neighbors, octopuses who gather at feeding sites with abundant food and competition for it sometimes throw silt at each other.

Crows understand the concept of recursion as well as children, and better than macaque monkeys. 

Wild Chimpanzees display declarative referential gesturing.








Friday, December 02, 2022

The Z-Library Kerfuffle and the whack-a-mole problem

Several months ago a friend told me about the Z-Library that he was using to download recently published fiction to evaluate candidates for book club reading. He thought it was sanctioned by publishers. I checked it out, decided to download a book, the book looked promising, so I bought the Amazon Kindle version. As this New York Daily News article makes clear in its description of the seizing of many Z-Library domains by the FBI, it is a pirate site, a file sharing service that evades copyright restrictions. I asked Wikipedia about Z-Library, and brought up a page with a description not only of Z-Library and its recent shut down in the U.S., but learned about the existence of many shadow libraries scattered over many different countries accessed by several metasearch engines. A box on this page, partly shown in the screen clip below, indicates it is part of a series on file sharing. I went to Anna's Archive, one of sites mentioned under the heading of Academic file sharing, and was able to easily download the entire text of a copyrighted Amazon Kindle Book I had purchased. Given the thousands of motivated individuals around the world who can't afford or don't have access to publications they need or want, there seems little prospect of denting the anarchy that prevails.